Pinned Tweet
Depth Beyond Pixels 🚀
We Introduce InfiniDepth — casting monocular depth estimation as a neural implicit field.
🔍 Arbitrary-Resolution
📐 Accurate Metric Depth
📷 Single-View NVS under large viewpoints shifts
Arxiv: arxiv.org/abs/2601.03252
page: zju3dv.github.io/InfiniDepth
Hao Yu retweeted
Made this 3D character from a reference image with Astra 6.2 + my 3D harness.
It feels like Astra’s 3D generation has taken another step forward. 🤯
Hao Yu retweeted
The InfiniSplat team have released v3 as SplatAnything. Just 22 days between the v2 and v3 papers 🤯
V2 could already turn overlapping photos into a Gaussian splat without training each scene from scratch. In v3, the team uses the spacing between splats to help decide how big they should be. Too small and you see gaps, while too much overlap softens the detail.
V3 is designed to get that balance right whether you’re scanning an apple on a desk or a whole city block.
Thrilled to release InfiniSplat v3 (SplatAnything)!
We teamed up with @TencentHunyuan to scale up InfiniSplat v2’s training data & introduced Gaussian Spacing Normalization for high-quality rendering across all scales, from object to aerial.
Code is now open-source👇
Hao Yu retweeted
A tabletop. A room. A city.
SplatAnything reconstructs them with the same feed-forward 3D model. The key is normalizing Gaussian spacing, rather than scene size alone.
Here's the idea in 3 minutes.
#3DGS #ComputerVision
Thrilled to release InfiniSplat v3 (SplatAnything)!
We teamed up with @TencentHunyuan to scale up InfiniSplat v2’s training data & introduced Gaussian Spacing Normalization for high-quality rendering across all scales, from object to aerial.
Code is now open-source👇
Excited to share SplatAnything!
From everyday objects and human subjects to expansive aerial scenes, SplatAnything transforms simple captures into 3D Gaussian scenes in few seconds. Give it a Try!
🌐 Project Page: zju3dv.github.io/SplatAnythi…
🤗 Huggingface: huggingface.co/spaces/ritian…
We tested some cases with only a single image as input, and the results are impressive! Give SplatAnything a try and turn any image you love into 3D!
Excited to share SplatAnything!
From everyday objects and human subjects to expansive aerial scenes, SplatAnything transforms simple captures into 3D Gaussian scenes in few seconds. Give it a Try!
🌐 Project Page: zju3dv.github.io/SplatAnythi…
🤗 Huggingface: huggingface.co/spaces/ritian…
Fable 5.2 shows substantially improved skills in controlling physical robots, even on tasks it has never explicitly been trained to do.
On RoboDojo, a benchmark with a simulated two-arm robot, it outperformed other models and most AI systems built to control robots.
SplatAnything
Gaussian Spacing Normalization for Feed-forward 3DGS across Arbitrary Scenes
paper: huggingface.co/papers/2611.0…
Hao Yu retweeted
SplatAnything
Gaussian Spacing Normalization for feed-forward 3DGS across arbitrary scenes.
From objects and people to aerial views, this method reconstructs 3D Gaussian scenes from simple captures with state-of-the-art quality.
Hao Yu retweeted
⚡️Reconstruct Gaussian splattings in seconds for objects, rooms, and even cities.
Excited to share SplatAnything!
From everyday objects and human subjects to expansive aerial scenes, SplatAnything transforms simple captures into 3D Gaussian scenes in few seconds. Give it a Try!
🌐 Project Page: zju3dv.github.io/SplatAnythi…
🤗 Huggingface: huggingface.co/spaces/ritian…
Excited to introduce SuperNav — bringing CodeX-like agents into the physical world!
🧭 Can accomplish any task in any scene.
📊 Thousands of navigation tasks tested on Habitat-GS, AI2-THOR & HM3D.
🤖 Deployed on a real robot.
👉 Code: github.com/zju3dv/SuperNav
Hao Yu retweeted
Introducing OM-1, our first robot foundation model, zero-shot generalizing to any robot: table-top arms, industrial arms and humanoids.
- learned directly from human manipulation data
- no teleop/robot data
- close to human-level dexterity and efficiency
- multi-robot collab
Hao Yu retweeted
Introducing Atlas:
The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D.
Model the world, move the camera, and simulate space & time.
Hao Yu retweeted
I’m incredibly excited to introduce @VeedaAI , which I co-founded with my incredible longtime collaborators @ZGojcic and @HuanLing6 .
We started Veeda because we believe robotics will reshape the world—changing how we move people and goods, how we manufacture and build, and how we operate in the physical world.
We also firmly believe that the scaling moment for Physical AI will come from robots learning through interaction with the world.
Just like humans learn from interaction with their environments by trying, failing and trying again, until we succeed. And just like the capabilities of LLMs were truly unlocked when they started training in interactive environments and not only on vast amounts of internet text.
For Physical AI, the central challenge is making this kind of interactive learning possible at scale. The real world is simply not a practical training ground for robots to learn through trial and error. It is unsafe, expensive, and time-consuming. To scale interactive learning, robots will need to learn in simulated reality.
At Veeda, our sole mission is to build simulated reality for Physical AI. Our conviction is that this will become the critical infrastructure layer for all areas of robotics.
As envisioned in pop culture, this means building “the Matrix” for Physical AI, where, through a virtual embodiment, robot intelligence can interact with an entirely virtual world in a million possible ways, learning from its own mistakes.
We believe that World Models are the foundational technology that can make this possible. These generative models learn from massive amounts of sensor and physical-world data to reach the quality, diversity, and physical realism of the simulated reality that robots require.
I could not be more excited to take on this challenge and build this transformative technology alongside an extraordinary team of engineers and researchers who have spent years working on some of the hardest problems across simulation, generative AI, 3D, robotics, and embodied intelligence.
Together with our investors at @khoslaventures and @radicalvcfund , we intend to push the frontier of this technology and build the foundational infrastructure for interactive robotics learning and evaluation at scale.
Come build this future with us.
And to roboticists, help us understand what you need, we’re building this for you.
veeda.ai
Hao Yu retweeted
Single video in, 4D human out.
4DAnyone turns a casual monocular video into a 4DGS model.
No camera rig, no calibration, no tripod.
Project: 4danyone.github.io/
Ever wanted to turn your photo album into a 3D world?
Check out our paper, InfiniSplat (SIGGRAPH Asia 2026), which turns a single image into an explorable 3D world. Great work by Jiawei @PLUS_W8VE !
🔗Project: zju3dv.github.io/InfiniSplat…
🤗Huggingface: huggingface.co/spaces/PLUS-W…
1
8
445
















